Apple M4 Pro GPU (20-core) vs Nvidia GeForce GTX 1660 SUPER
40
out 100
VS
23
out 100
Compared 2 processors: Apple M4 Pro GPU (20-core), vs Nvidia GeForce GTX 1660 SUPER. Below are specs, tests, pros and cons for each device
Review
Games
Performance in DirectX, OpenCL, Vulkan
AI/ML
AI workload testing
Professional Apps
3D modeling, video editing, rendering
Energy Efficiency
Power usage in various scenarios
Tests & specs
Specs & test comparisonGames
| Game title | 1080p (High) 1080p (Ultra) 1440p (Ultra) 4K (Ultra) | |
 Forza Horizon 5 | n/a n/a n/a n/a | 88 53 43 26 |
 The Witcher 3 | n/a n/a n/a n/a | 80 63 43 22 |
 Counter-Strike 2 | n/a n/a n/a n/a | 131 93 68 28 |
 Far Cry 6 | n/a n/a n/a n/a | 71 62 46 23 |
 Hogwarts Legacy | n/a n/a n/a n/a | 44 36 28 13 |
 COD Modern Warfare 3 | n/a n/a n/a n/a | 56 44 32 20 |
 Ghost of Tsushima | n/a n/a n/a n/a | 43 34 22 13 |
 Cyberpunk 2077 | n/a n/a n/a n/a | 44 39 22 10 |
 Shadow of the Tomb Raider | n/a n/a n/a n/a | 77 71 47 23 |
| 1080p High | n/a | 70 |
| 1080p Ultra | n/a | 55 |
| 1440p Ultra | n/a | 39 |
| 4K Ultra | n/a | 20 |
| Deviation | n/a | Low |
Benchmarks
| Time Spy | n/a | 6047 |
| Solar Bay | n/a | 19265 |
| Port Royal | n/a | 1549 |
| Fire Strike | n/a | 16183 |
| Night Raid | n/a | 74430 |
| Background Blur | 125.1 frames/s | 122.5 frames/s |
| Face Detection | 80 frames/s | 68.6 frames/s |
| Horizon Detection | 2.88 Gpix/sec | 2.56 Gpix/sec |
| Edge Detection | 4.22 Gpix/sec | 3.33 Gpix/sec |
| Gaussian Blur | 2.98 Gpix/sec | 3.21 Gpix/sec |
| Feature Matching | 0.8 Gpix/sec | 0.86 Gpix/sec |
| Stereo Matching | 235 Gpix/sec | 273.3 Gpix/sec |
| Particle Physics | 9516.1 fps | 8476.3 fps |
| API | OpenCL | OpenCL |
| G2D Mark | n/a | 804 |
| DirectX 11 | n/a | 103 fps |
| DirectX 12 | n/a | 49 fps |
| GPU Compute | n/a | 5099 Ops/s |
| Aztec Ruins (Normal) | 757.5 fps | 396.1 fps |
| Car Chase | 576.2 fps | 339.7 fps |
| Manhattan 3.1.1 (1440p) | 473.2 fps | 304.7 fps |
| T-Rex | 2148.5 fps | 1502.8 fps |
| ALU 2 | 912.2 fps | 1607.1 fps |
| Driver Overhead 2 | 535.8 fps | 272.1 fps |
| API | Metal | OpenGL |
| OS | OS X | Windows |
| Tessellation | n/a | 1760.2 |
Tech Specs
Specs & test comparisonGeneral Info
| Manufacturer | Apple | Nvidia |
| Build | Integrated | Discrete |
| Announced | October, 29, 2024 | October, 29, 2019 |
| Form Factor | Laptop use | PC use |
| Use case | Professional | Gaming |
| Segment | Mid-range | Entry-level |
| Architecture | Apple M GPU | Turing |
| Codename | Custom | TU116 |
| Price | n/a | 229 |
GPU
| GPU Frequency | 500 MHz | 1530 MHz |
| Boost GPU Frequency | 1800 MHz | 1785 MHz |
| Shader Units | 2560 | 1408 |
| TMUs | 160 | 88 |
| ROPs | 80 | 48 |
| Execution Units | 320 | 22 |
| Ray Tracing Cores | n/a | No |
| Tensor Cores | n/a | No |
| L1 cache | n/a | 64 KB/core |
| L2 cache | n/a | 1536 KB/core |
| Instructions per Clock | 2 IPC | 2 IPC |
Performance
| Pixel Fill Rate | 144 Gpix/sec | 86 Gpix/sec |
| Texture Fill Rate | 288 GTex/s | 157 GTex/s |
| FLOPS | 9.2 TFLOPS | 5 TFLOPS |
Process
| Interface | Custom | PCIe 3.0 x16 |
| TGP | 32 W | 125 W |
| Process | TSMC | TSMC |
| Process tech. | 3 nm | 12 nm |
| Max temperature | 100 °C | n/a |
| Transistor Size | n/a | 284 mm² |
| Transistor count | n/a | 6 billion |
| Transistor density | n/a | 21.13 MTr/mm² |
Memory
| Interface | System Shared | GDDR6 |
| Memory Frequency | 7500 MHz | 1750 MHz |
| Bus | 192 bit | 192 bit |
| ECC support | No | No |
| Effective Memory Speed | 15000 MB/s | 14000 MB/s |
| Memory Size | n/a | 6 GB |
Max Throughput
API
| DirectX | n/a | 12 |
| Vulkan | n/a | 1.3 |
| OpenGL | n/a | 4.6 |
| CUDA | n/a | 7.5 |
| DisplayPort | n/a | 1.4a |
| Ray Tracing | Yes | No |
| DLSS | No | No |
Results
After analyzing the data, we consider Apple M4 Pro GPU (20-core) the clear winner in this comparison.
Survey
Total Votes: 1
